diff options
Diffstat (limited to 'test/CodeGen/R600/fabs.ll')
| -rw-r--r-- | test/CodeGen/R600/fabs.ll | 123 |
1 files changed, 78 insertions, 45 deletions
diff --git a/test/CodeGen/R600/fabs.ll b/test/CodeGen/R600/fabs.ll index b87ce22..06cc97f 100644 --- a/test/CodeGen/R600/fabs.ll +++ b/test/CodeGen/R600/fabs.ll @@ -1,65 +1,98 @@ -; RUN: llc < %s -march=r600 -mcpu=redwood | FileCheck %s --check-prefix=R600-CHECK -; RUN: llc < %s -march=r600 -mcpu=SI -verify-machineinstrs | FileCheck %s --check-prefix=SI-CHECK +; RUN: llc -march=r600 -mcpu=SI -verify-machineinstrs < %s | FileCheck -check-prefix=SI -check-prefix=FUNC %s +; RUN: llc -march=r600 -mcpu=redwood < %s | FileCheck -check-prefix=R600 -check-prefix=FUNC %s + ; DAGCombiner will transform: ; (fabs (f32 bitcast (i32 a))) => (f32 bitcast (and (i32 a), 0x7FFFFFFF)) ; unless isFabsFree returns true -; R600-CHECK-LABEL: @fabs_free -; R600-CHECK-NOT: AND -; R600-CHECK: |PV.{{[XYZW]}}| -; SI-CHECK-LABEL: @fabs_free -; SI-CHECK: V_AND_B32 +; FUNC-LABEL: {{^}}fabs_fn_free: +; R600-NOT: AND +; R600: |PV.{{[XYZW]}}| + +; SI: v_and_b32 + +define void @fabs_fn_free(float addrspace(1)* %out, i32 %in) { + %bc= bitcast i32 %in to float + %fabs = call float @fabs(float %bc) + store float %fabs, float addrspace(1)* %out + ret void +} + +; FUNC-LABEL: {{^}}fabs_free: +; R600-NOT: AND +; R600: |PV.{{[XYZW]}}| + +; SI: v_and_b32 define void @fabs_free(float addrspace(1)* %out, i32 %in) { -entry: - %0 = bitcast i32 %in to float - %1 = call float @fabs(float %0) - store float %1, float addrspace(1)* %out + %bc= bitcast i32 %in to float + %fabs = call float @llvm.fabs.f32(float %bc) + store float %fabs, float addrspace(1)* %out + ret void +} + +; FUNC-LABEL: {{^}}fabs_f32: +; R600: |{{(PV|T[0-9])\.[XYZW]}}| + +; SI: v_and_b32 +define void @fabs_f32(float addrspace(1)* %out, float %in) { + %fabs = call float @llvm.fabs.f32(float %in) + store float %fabs, float addrspace(1)* %out + ret void +} + +; FUNC-LABEL: {{^}}fabs_v2f32: +; R600: |{{(PV|T[0-9])\.[XYZW]}}| +; R600: |{{(PV|T[0-9])\.[XYZW]}}| + +; SI: v_and_b32 +; SI: v_and_b32 +define void @fabs_v2f32(<2 x float> addrspace(1)* %out, <2 x float> %in) { + %fabs = call <2 x float> @llvm.fabs.v2f32(<2 x float> %in) + store <2 x float> %fabs, <2 x float> addrspace(1)* %out ret void } -; R600-CHECK-LABEL: @fabs_v2 -; R600-CHECK: |{{(PV|T[0-9])\.[XYZW]}}| -; R600-CHECK: |{{(PV|T[0-9])\.[XYZW]}}| -; SI-CHECK-LABEL: @fabs_v2 -; SI-CHECK: V_AND_B32 -; SI-CHECK: V_AND_B32 -define void @fabs_v2(<2 x float> addrspace(1)* %out, <2 x float> %in) { -entry: - %0 = call <2 x float> @llvm.fabs.v2f32(<2 x float> %in) - store <2 x float> %0, <2 x float> addrspace(1)* %out +; FUNC-LABEL: {{^}}fabs_v4f32: +; R600: |{{(PV|T[0-9])\.[XYZW]}}| +; R600: |{{(PV|T[0-9])\.[XYZW]}}| +; R600: |{{(PV|T[0-9])\.[XYZW]}}| +; R600: |{{(PV|T[0-9])\.[XYZW]}}| + +; SI: v_and_b32 +; SI: v_and_b32 +; SI: v_and_b32 +; SI: v_and_b32 +define void @fabs_v4f32(<4 x float> addrspace(1)* %out, <4 x float> %in) { + %fabs = call <4 x float> @llvm.fabs.v4f32(<4 x float> %in) + store <4 x float> %fabs, <4 x float> addrspace(1)* %out ret void } -; R600-CHECK-LABEL: @fabs_v4 -; R600-CHECK: |{{(PV|T[0-9])\.[XYZW]}}| -; R600-CHECK: |{{(PV|T[0-9])\.[XYZW]}}| -; R600-CHECK: |{{(PV|T[0-9])\.[XYZW]}}| -; R600-CHECK: |{{(PV|T[0-9])\.[XYZW]}}| -; SI-CHECK-LABEL: @fabs_v4 -; SI-CHECK: V_AND_B32 -; SI-CHECK: V_AND_B32 -; SI-CHECK: V_AND_B32 -; SI-CHECK: V_AND_B32 -define void @fabs_v4(<4 x float> addrspace(1)* %out, <4 x float> %in) { -entry: - %0 = call <4 x float> @llvm.fabs.v4f32(<4 x float> %in) - store <4 x float> %0, <4 x float> addrspace(1)* %out +; SI-LABEL: {{^}}fabs_fn_fold: +; SI: s_load_dword [[ABS_VALUE:s[0-9]+]], s[{{[0-9]+:[0-9]+}}], 0xb +; SI-NOT: and +; SI: v_mul_f32_e64 v{{[0-9]+}}, |[[ABS_VALUE]]|, v{{[0-9]+}} +define void @fabs_fn_fold(float addrspace(1)* %out, float %in0, float %in1) { + %fabs = call float @fabs(float %in0) + %fmul = fmul float %fabs, %in1 + store float %fmul, float addrspace(1)* %out ret void } -; SI-CHECK-LABEL: @fabs_fold -; SI-CHECK-NOT: V_AND_B32_e32 -; SI-CHECK: V_MUL_F32_e64 v{{[0-9]+}}, s{{[0-9]+}}, |v{{[0-9]+}}| +; SI-LABEL: {{^}}fabs_fold: +; SI: s_load_dword [[ABS_VALUE:s[0-9]+]], s[{{[0-9]+:[0-9]+}}], 0xb +; SI-NOT: and +; SI: v_mul_f32_e64 v{{[0-9]+}}, |[[ABS_VALUE]]|, v{{[0-9]+}} define void @fabs_fold(float addrspace(1)* %out, float %in0, float %in1) { -entry: - %0 = call float @fabs(float %in0) - %1 = fmul float %0, %in1 - store float %1, float addrspace(1)* %out + %fabs = call float @llvm.fabs.f32(float %in0) + %fmul = fmul float %fabs, %in1 + store float %fmul, float addrspace(1)* %out ret void } -declare float @fabs(float ) readnone -declare <2 x float> @llvm.fabs.v2f32(<2 x float> ) readnone -declare <4 x float> @llvm.fabs.v4f32(<4 x float> ) readnone +declare float @fabs(float) readnone +declare float @llvm.fabs.f32(float) readnone +declare <2 x float> @llvm.fabs.v2f32(<2 x float>) readnone +declare <4 x float> @llvm.fabs.v4f32(<4 x float>) readnone |